EP4254385A1 - Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette - Google Patents

Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette Download PDF

Info

Publication number
EP4254385A1
EP4254385A1 EP22165039.3A EP22165039A EP4254385A1 EP 4254385 A1 EP4254385 A1 EP 4254385A1 EP 22165039 A EP22165039 A EP 22165039A EP 4254385 A1 EP4254385 A1 EP 4254385A1
Authority
EP
European Patent Office
Prior art keywords
road user
risk level
current risk
image
threshold
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
EP22165039.3A
Other languages
German (de)
English (en)
Inventor
Andreas Galos
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Alps Alpine Europe GmbH
Original Assignee
Alps Alpine Europe GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Alps Alpine Europe GmbH filed Critical Alps Alpine Europe GmbH
Priority to EP22165039.3A priority Critical patent/EP4254385A1/fr
Publication of EP4254385A1 publication Critical patent/EP4254385A1/fr
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62J—CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
    • B62J27/00—Safety equipment
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B62—LAND VEHICLES FOR TRAVELLING OTHERWISE THAN ON RAILS
    • B62J—CYCLE SADDLES OR SEATS; AUXILIARY DEVICES OR ACCESSORIES SPECIALLY ADAPTED TO CYCLES AND NOT OTHERWISE PROVIDED FOR, e.g. ARTICLE CARRIERS OR CYCLE PROTECTORS
    • B62J50/00—Arrangements specially adapted for use on cycles not provided for in main groups B62J1/00 - B62J45/00
    • B62J50/20—Information-providing devices
    • B62J50/21—Information-providing devices intended to provide information to rider or passenger
    • B62J50/22—Information-providing devices intended to provide information to rider or passenger electronic, e.g. displays
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • B60Q9/008—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling for anti-collision purposes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2300/00—Indexing codes relating to the type of vehicle
    • B60W2300/36—Cycles; Motorcycles; Scooters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo or light sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera

Definitions

  • the invention relates to a method for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the invention is directed to a data processing device for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the invention relates to a system for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the invention is also directed to a bicycle assembly comprising a bicycle and a system as described above.
  • an interference between road users is to be understood as an undesired influence of one road user, e.g. the second road user, on the other road user, e.g. the first road user.
  • a simple example of an interference is a collision between the road users.
  • An interference may also be called a hazard or hazard event.
  • a situation in which an interference takes place may be designated as a hazardous situation.
  • warning devices being configured for warning a road user of other road users which are located on a rear side. Such devices are especially known for bicycles. If a road user being located on the rear side is detected, a warning is issued which can be an audio warning, a visual warning or a combined audio warning and visual warning.
  • the problem to be solved by the present invention is to improve such warning devices and corresponding methods.
  • the problem is solved by a method for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the method comprises:
  • the method uses at least one image taken from a position of the first road user as an input. Preferably, not only one image but rather a set or a stream of images is received.
  • a current risk level indicator is generated by analyzing the at least one image.
  • the risk level indicator describes a current risk of interference, i.e. a risk of interference prevailing at the time of analyzing the at least one image.
  • the steps of receiving the at least one image and analyzing the received image may be summarized as monitoring a rearward traffic situation.
  • the current risk level threshold describes the risk level threshold that is applicable at the time of executing the method. Thus, the current risk level threshold is variable and may change from one point in time to another point in time.
  • the current risk level threshold may be provided automatically, i.e. without the interaction of a user.
  • the current risk level threshold is determined based on a risk level history. Consequently, the current risk level threshold may be high if the set of historic risk level indicators comprises predominantly high risk level indicators. This may be the case if the method is performed in an environment with heavy traffic, e.g. on a city road. In such a situation, due to the comparatively high current risk level threshold, only comparatively high current risk level indicators will lead to a notification of the first road user.
  • the current risk level threshold may be low if the set of historic risk level indicators comprises predominantly low risk level indicators. This may be the case if the method is performed in an environment with little traffic, e.g. on a country road. In such a situation, due to the comparatively low current risk level threshold, also comparatively low current risk level indicators will lead to a notification of the first road user. Altogether, the notifications are adaptable to a general risk level prevailing in the environment in which the method is performed. In each of the varying situations an appropriate and effective notification can be provided to the first road user thereby enhancing road safety.
  • the effects and advantages of the method according to the present invention will become especially clear when considering the following example in which a method operating with a fixed, pre-set risk level threshold is compared to the method according to the invention.
  • the fixed, pre-set risk level threshold may be suitable for generating a reasonable amount of notifications with a reasonable forecast in a country road setting. If the same method with the same pre-set risk level threshold is executed in a heavy traffic situation, e.g. on a city road, the first road user will receive a multitude of notifications, i.e. too many. Moreover, the notifications may be too early. The first road user will be overburdened such that the first road user is not able to distinguish vital notifications from notifications just reflecting the general risk level in the heavy traffic situation.
  • the fixed, pre-set risk level threshold may be suitable for generating a reasonable amount of notification with a reasonable forecast in a heavy traffic situation. If the same method with the same pre-set risk level threshold is executed in a country road setting with little traffic, the first road user will be notified only in situations of comparatively high risk. Thus, there may be too few notifications. Moreover, the notifications may be provided too late. This may provide undue stress on the first road user since he or she has to react very quickly to this notification. The undue stress may compensate the benefits of the notification such that overall road safety is not improved. When using the method according to the present invention, these problems are solved and the first road user will neither be overburdened in the heavy traffic situation nor be unduly stressed in the country road situation.
  • the triggered notification may be a visual notification, an audio notification or a combined visual notification and audio notification.
  • the notification may comprise a warning.
  • the method additionally comprises calculating a difference between the current risk level indicator and the current risk level threshold.
  • the current risk level indicator may be classified, e.g. as a high risk, a middle risk or a low risk.
  • the notification for the road user may be a function of the classification of the current risk level indicator.
  • a color may change.
  • yellow color may be used for a low risk, orange color for a middle risk and red color for a high risk.
  • the degree of loudness may be adapted in accordance with the classification of the risk. It is also possible to define a frequency or a frequency band of the notification as a function of the classification.
  • analyzing the received image comprises estimating at least one of a time to pass the first road user, a passing distance and a passing speed of the at least one second road user based on the received image.
  • the estimated time to pass is the estimated time until the second road user passes by first road user.
  • the estimated passing distance is the estimated lateral distance between the first road user and the second road user when the second road user passes by the first road user.
  • the estimated passing speed is the estimated relative velocity between the first road user and the second road user when the second road user is passing by the first road user.
  • the risk level indicator may correspond to a weighted product or a weighted sum of the estimated time to pass, the estimated passing distance and the estimated passing speed.
  • a weighted product each of the parameters mentioned before is multiplied with a corresponding weight in a first step.
  • the weighted parameters are multiplied with one another.
  • a weighted sum each of the parameters mentioned before is multiplied with a corresponding weight in a first step.
  • the sum of the weighted parameters is calculated.
  • the weights can be pre-set.
  • the weighted parameters may be normalized before being multiplied or summed up.
  • the weighted product and the weighted sum both are simple, but realistic models of the influence of the parameters mentioned above on the risk level. Consequently, the risk level may be easily and accurately calculated using the weighted product or the weighted sum.
  • At least one of a first weight for weighting the estimated time to pass, a second weight for weighting the estimated passing distance, and a third weight for weighting the estimated passing speed is a function of a driving behavior or a user setting.
  • a user may set at least one of the first weight, the second weight and the third weight according to his or her preferences.
  • a driving behavior may be described by at least one of a current position of the first road user, a current speed of the first road user, a historic speed of the first road user, a current acceleration of the road user, and a historic acceleration of the road user.
  • the historic parameters may for example be provided in the form of a historic average or a historic maximum. In the case of an acceleration, one may distinguish longitudinal and lateral acceleration.
  • the at least one of the first weight, the second weight and the third weight may be determined as function of at least one of the parameters describing the driving behavior.
  • the weights for a rather diverse or aggressive first road user may be different from the weights for a rather cautious first road user. Thus, each of these road user types will be provided with appropriate notifications.
  • the method further comprises triggering the notification for the first road user if the estimated time to pass is lower than a time threshold or if the estimated passing distance is lower than a distance threshold or if the estimated passing speed exceeds a speed threshold.
  • the notification is triggered independent from the current risk level indicator.
  • Such a functionality may be designated as an override functionality.
  • a notification is triggered if the second road user passed by the first road user in a comparatively short estimated time, at a comparatively low estimated distance of with a comparatively high estimated speed.
  • the time threshold is between 1 second and 5 seconds, e.g. 2 seconds
  • the distance threshold is between 0 meters and 0,5 meters, e.g. 0,1 meters or 0,2 meters
  • the speed threshold is between 20 km/h and 70km/h, e.g. 30 km/h or 50 km/h.
  • Such an override functionality further enhances road safety.
  • At least one of the time threshold, the distance threshold, and the speed threshold may be a function of a driving behavior or a user setting. In the latter case, as before, a user may set at least one of the thresholds according to his or her preferences.
  • a driving behavior may be described by the same parameters that have been described in connection with the at least one of the first weight, the second weight and the third weight.
  • the at least one threshold may be determined as function of at least one of the parameters describing the driving behavior.
  • the thresholds for a rather diverse or aggressive first road user may be different from the weights for a rather cautious first road user. More generally speaking, the sensitivity of the override functionality may be adapted. Thus, each of these road user types will be provided with appropriate notifications caused by the override functionality.
  • the current risk level threshold corresponds to an average of a set of historic risk level indicators over a defined time window in the past.
  • Such an average may be designated as a floating average.
  • the time window in the past may be for example 5 seconds to 40 seconds, e.g. 10 seconds, 20 seconds or 30 seconds.
  • Such a risk level threshold is highly adaptive with respect to changing traffic conditions, more precisely highly adaptive with respect to a changing general risk level.
  • the average may also be a weighted average.
  • older risk level indicators may have a lower weight than younger risk level indicators.
  • the recent past is more relevant when calculating the risk level threshold than the earlier past.
  • the current risk level threshold leads to appropriate notifications for the prevailing traffic situation.
  • the current risk level threshold corresponds to an average of a set of historic risk level indicators corresponding to a defined number of past notification events. As before, such an average may be called a floating average. However, now only the risk level indicators which have led to a notification event are considered. The remaining risk level indicators are not used for calculating the average. In a variant, the average may be a weighted average. This means that for example older risk level indicators may have a lower weight than younger risk level indicators. Thus, the recent past is more relevant when calculating the risk level threshold than the earlier past. Overall, the current risk level threshold leads to appropriate notifications for the prevailing traffic situation.
  • analyzing the received image comprises applying a machine vision technique.
  • the image may be analyzed automatically within a short time and with a high reliability.
  • the current risk level indicator may be deducted automatically. Due to the accurate nature of machine vision techniques, also the deducted risk level indicator is accurate. It is noted that in a case in which more than one second road users are shown in the at least one image, a current risk level indicator is deducted for each of these second road users.
  • applying a machine vision technique comprises applying a segmentation technique. This means that the received at least one image is segmented before the current risk level indicator is deducted. In a preferred variant, one segment is generated for each second road user. The remaining segments of the received image are not relevant for generating the current risk level indicator and, thus, may be ignored. This enhances the computational efficiency of the machine vision technique.
  • a trained convolutional neural network is used for performing the segmentation.
  • This neural network may be trained with images showing vehicles, e.g. cars and trucks, which are the most relevant second road users.
  • Such training data is publicly available.
  • the segmentation is done by generating a differential image. This means that a difference is calculated between two temporally sequential images. The difference just shows the portions of the image where objects being shown in the image have moved. Thus, a segment may be defined for each moving object.
  • Generating a differential image is a very simple and computationally efficient method for generating segments comprising moving objects.
  • the machine vision technique may comprise an optical flow technique.
  • the optical flow technique is known as such. This technique uses a set of temporally sequential images which may be designated as frames. Each pixel of each of these images is either defined by a brightness value and a color value or by a brightness value, a red color value, a green color value, and a blue color value.
  • the optical flow technique searches for pixels having the same characteristic, i.e. the same values as explained above, in subsequent images. Subsequently, a path or a trajectory of each pixel may be determined over the set of temporally sequential images.
  • the optical flow technique may be used for segmenting the images. The optical flow technique is especially performant with respect to the detection of moving objects in a set of images.
  • segments comprising second road users may be generated in an efficient and reliable manner.
  • the trajectories or paths are used for deducting the current risk level indicator.
  • the paths or trajectories are extrapolated such that a time to pass, a passing speed and a passing distance may be estimated.
  • the current risk level indicator may be determined with high efficiency, accuracy and reliability.
  • the optical flow technique may be used for both segmentation and deduction of the current risk level indicator. In such a case, only the segments comprising a second road user may be considered for deducting the current risk level indicator.
  • the optical flow technique is very tolerant with respect to color and brightness. This means that the optical flow technique is also very tolerant with respect to camera interference and artefacts.
  • the optical flow technique produces reliable results independent from light conditions which may be influenced for example by weather conditions.
  • the method comprises providing the received image to the first road user. Consequently, the first road user is able to observe the rear traffic.
  • This functionality can be designated as a digital rear view mirror.
  • the notifications may be provided as an overlay over the image or in combination with the image. In such a configuration the first road user may perceive the current risk level very easily and quickly. This further enhances road safety.
  • the method according to the invention may be computer-implemented.
  • the method may be implemented in software or in hardware, or in software and hardware. Further, the method may be carried out by computer program instructions running on means that provide data processing functions.
  • the data processing means may be a suitable computing means, such as a mobile electronic device or an electronic control module, which may also be a distributed computer system.
  • the data processing means or the computer respectively, may comprise one or more of a processor, a memory, a data interface, or the like.
  • a data processing device for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the data processing device comprises means configured for carrying out the method according to the invention.
  • Such a data processing devices is, thus, configured to provide notifications for the first road user which are adaptable to a general risk level prevailing in the environment in which the data processing device is used. An appropriate and effective notification of the first road user enhances road safety.
  • the data processing device may be a component of a smart phone, a tablet, a smart watch or any other portable electronic device.
  • the data processing device is a specific stand-alone device which may be mounted on or at the first road user.
  • the method according to the invention may be executed on each of these devices.
  • the problem is solved by a system for assessing a risk of interference between a first road user, especially a cyclist, and at least one second road user being located behind the first road user.
  • the system comprises a data processing device according to the invention.
  • the system comprises an image capturing device being configured to capture at least one image from a position of the first road user showing a traffic situation including the at least one second road user.
  • the system comprises a notification interface configured to provide a notification for the first road user.
  • the image capturing device is communicatively connected to the data processing device and the notification interface is communicatively connected to the data processing device.
  • the notifications are adaptable to a general risk level prevailing in the environment in which the system is used. Consequently, the notifications are appropriate and effective for the respective environment. This enhances road safety.
  • the system according to the invention may be called a situational risk assessment system for rear traffic monitoring or a rear traffic alert system.
  • the system may further comprise an image interface being configured for providing an image captured by the image capturing device to the first road user.
  • the image interface may be communicatively connected to at least one of the image capturing device and the data processing device. Consequently, the system offers a rearview mirror functionality to the first road user.
  • the first road user thus, can observe the rear traffic independent from a risk of interference and independent from a notification.
  • the notifications can be provided as an overlay over the image or in combination with the image. In such a configuration the first road user may perceive the current risk level very easily and quickly. This further enhances road safety.
  • a bicycle assembly comprising a bicycle and a system according to the invention.
  • the system is mounted on the bicycle such that the image capturing device is facing rearwards.
  • the image capturing device may be mounted on a saddle post or on a rear portion of the bicycle's frame.
  • Figure 1 shows a traffic situation wherein on a road 10 a first road user 12 travels along a corresponding first travelling direction 14 and a second road user 16 travels along a corresponding second travelling direction 18.
  • the second road user 16 is located behind the first road user 12. It is noted that this relative orientation of the first road user 12 and the second road user 16 is independent from the fact whether at least one of the first road user 12 and the second road user 16 is moving or not.
  • the first road user 12 is a cyclist 20.
  • the second road user 16 is a car 22.
  • the first road user 18 is formed by a person which is omitted in the figures for the ease of representation which is using a bicycle assembly 24.
  • the bicycle assembly 24 is shown in more detail in Figure 2 .
  • the bicycle assembly 24 comprises a bicycle 26 which is only partly shown in Figure 2 and a system 28 for assessing a risk of interference between the first road user 12, i.e. the cyclist 20, and the second road user 16, i.e. the car 22, being located behind the first road user 12.
  • the system 28 comprises two components 28a, 28b.
  • a first component 28a is mounted on a seat post 30 of the bicycle 26 such that it faces rearwards, i.e. in an orientation opposite to the first travelling direction 14.
  • a second component 28b is mounted on a handle bar 32 of the bicycle 26 such that it is easily visible by the person riding the bicycle 26.
  • the first component 28a and the second component 28b are connected by a wireless data connection 34 illustrated by an arrow in Figure 2 .
  • the system 28 is shown in more detail in Figure 3 .
  • the system 28 comprises an image capturing device 36.
  • the image capturing device 36 is arranged within the first component 28a and the first component 28a is mounted on the seat post 30 such that the image capturing device 26 is facing rearwards.
  • the image capturing device 36 is configured to capture at least one image from a position of the first road user 12.
  • the at least one captured image shows a traffic situation including the second road user 16.
  • the system 28 also comprises a data processing device 38 and the image capturing device 36 is communicatively connected to the data processing device 38.
  • the data processing device 38 comprises an image receiving interface 40 which is communicatively connected to the image capturing device 36.
  • the image receiving interface 40 is configured to receive images I captured by the image capturing device 36.
  • the data processing device 38 also comprises an image analysis unit 42.
  • the image analysis unit 42 is communicatively connected to the image receiving interface 40.
  • the image analysis unit 42 is configured to analyze the received images I and deduct a current risk level indicator RLI describing a current risk of interference between the first road user 12 and the second road user 16. The calculation of the current risk level indicator RLI will be explained in detail further below.
  • the data processing device 38 comprises a current risk level threshold determination unit 44.
  • the current risk level threshold determination unit 44 comprises a storage unit 46. On the storage unit 46 a set of historic risk level indicators HRLI is stored. Moreover, the current risk level threshold determination unit 44 comprises a processing unit 48 which is communicatively connected to the storage unit 46.
  • the processing unit 48 of the current risk level threshold determination unit 44 is configured to determine a current risk level threshold RLT as a function of the set of historic risk level indicators. The determination of the current risk level threshold RLT will be explained in more detail further below.
  • the data processing device 38 further comprises a comparator unit 50 which is communicatively connected to both the image analysis unit 42 and the current risk level threshold determination unit 44.
  • the comparator unit 50 is configured to compare the current risk level indicator RLI which is provided by the image analysis unit 42 and the current risk level threshold RLT which his provided by current risk level threshold determination unit 44.
  • the data processing device 38 also comprises a triggering unit 52 which his configured to trigger a notification for the first road user 12 if the current risk level indicator RLI provided by the image analysis unit 42 exceeds the current risk level threshold RLT provided by the current risk level threshold determination unit 44.
  • the triggering unit 52 is communicatively connected to the comparator unit 50.
  • the triggering unit 52 or more generally speaking the data processing device 38 is communicatively connected to a notification interface 54.
  • the notification interface 54 forms part of the first component 28a and is configured for sending a notification the second component 28b using wireless data signal.
  • the system 28 can provide visual and audible notifications.
  • the second component 28b comprises an audio output unit 56 and a visual output unit 58, e.g. a screen.
  • Both the audio output unit 56 and the visual output unit 58 are connected to a notification receiving interface 60 which forms part of the second component 28b.
  • the notification receiving interface 60 is communicatively connected to the notification interface 54 via a wireless data connection.
  • the system 28 is also configured to provide a digital rear mirror functionality. This means that the system 28 is configured to provide the images I captured by the image capturing device 36 to the first road user 12.
  • the first component 28a comprises an image interface 62.
  • the image interface 62 is communicatively connected to the image capturing device 36 in a direct manner.
  • the image interface 62 is communicatively connected to an image receiving interface 64 of the second component 28b via a wireless data connection.
  • the image receiving interface 64 is communicatively connected to the visual output unit 58 such that an image I can be displayed to the first road user 12.
  • notification receiving interface 60 and the image receiving interface 64 are represented and explained as separate interfaces. However, it is also conceivable that the notification receiving interface 60 and the image receiving interface 64 are formed as a single, common interface.
  • the first component 28a is realized as a singular mounting unit 66. All of the building blocks of the first component 28a as described above thus form one integral unit. Since the mounting unit 66 comprises the image capturing device 36, it may be called a camera unit.
  • the second component 28b is realized as a smart phone 68 which is communicatively connected to the first component 28a via the wireless data connection 34, e.g. via a WiFi connection or a Bluetooth connection.
  • the first component 28a i.e. the mounting unit 66, only comprises the image capturing device 36.
  • the remaining building blocks of the system 28 are formed by the second component 28b, i.e. the smart phone 68.
  • the data processing device 38 and its sub-units is formed by one or more components of the smart phone 68.
  • the notification interface 54, the notification receiving interface 60, the image interface 62 and the image receiving interface 64 are now internal interfaces of the smart phone 68.
  • a further difference between the configuration of Figure 3 and the configuration of Figure 4 is that the image interface 62 is now connected to the image capturing device 36 via the data processing device 38, in more detail via the image receiving interface 40.
  • the data processing device 38 is configured for assessing a risk of interference between the first road user 12 and at second road user 16.
  • the data processing device 38 is configured to carrying out a method for assessing a risk of interference between the first road user 12 and the second road user 16 being located behind the first road user 12.
  • a first step S1 at least one image I is received.
  • the image receiving interface 40 is used for the performance of this step.
  • the images I are captured by the image capturing unit 36.
  • the images I are received in the form or a stream of images I.
  • the image I is taken from a position of the first road user 12 and shows a traffic situation including the second road user 16.
  • a current risk level indicator RLI is deducted.
  • the current risk level indicator RLI describes a current risk of interference between the first road user 12 and the second road user 16.
  • the current risk level indicator RLI corresponds to a weighted product of an estimated time to pass TTP, an estimated passing distance PD and an estimated passing speed PS of the second road user 16.
  • the parameters time to pass TTP, passing distance PD and passing speed PS are deducted from the received images I using a machine vision technique.
  • the optical flow technique is used to segment the received images I.
  • one segment is generated which comprises the second road user 16.
  • the remaining portions of the image I form a second segment which can be designated as background. The latter segment can be ignored for the following calculations.
  • trajectories for pixels can be generated based on temporally adjacent images I. This is done for the pixels representing the second road user 16. If these trajectories are extrapolated, the time to pass TTP can be estimated. Moreover, the passing distance PD and the passing speed PS of the second road user 16 can be estimated.
  • the weights W1, W2, W3 of the weighted product of the time to pass TTP, the passing distance PD and the passing speed PS are determined according to a user setting.
  • a current risk level threshold RLT is determined. To this end, the current risk level threshold determination unit 44 is used.
  • the current risk level threshold RLT corresponds to an average of a set of historic risk level indicators HRLI over a defined time window in the past.
  • the historic risk level indicators HRLI are provided by the storage unit 46 of the current risk level threshold determination unit 44.
  • a fourth step S4 the current risk level indicator RLI and the current risk level threshold RLT are compared. This is done by using the comparator unit 50.
  • step S5 a notification for the first road user 12 is triggered.
  • the triggering unit 52 is used.
  • both an audible and a visual notification are triggered such that a notification is output by the audio output unit 56 and the visual output unit 58.
  • the audible notification may comprise a warning sound such as a beep or a sequence of beeps.
  • the visual warning is integrated into the image I captured by the image capturing device 36 and provided to the first road user 12 via the image interface 62.
  • the visual notification can comprise different kinds of highlighting bars 70.
  • the notification can comprise a notification banner 72 as shown in Figure 6 (c) .
  • the highlighting bars 70 are colored as a function of a difference of the current risk level indicator RLI and the current risk level threshold RLT. Depending on the magnitude of the difference, the highlighting bars may be colored, e.g. in green, yellow, orange and/or red.
  • the method also comprises an override functionality.
  • a time threshold TT a time threshold TT, a distance threshold DT, and a speed threshold ST are defined by a user setting.
  • step S2 In a case in which in step S2 using the optical flow technique, it turns out that at least one of the estimated time to pass TTP is lower than the time threshold TT or if the estimated passing distance PD is lower than the distance threshold DT or if the estimated passing speed PS exceeds the speed threshold ST, a notification is triggered independent from the current risk level threshold RLT.
  • the time threshold TT, the distance threshold DT, and the speed threshold ST are defined such that a second road user 16 fulfilling one of the corresponding conditions alone would generate a high risk of interference.
  • the notification can be audible and visual as has already been explained above.
  • the image I is provided to the first road user 12 via the visual output unit 58.
  • the first road user can use the visual output unit 58 as a digital rearview mirror.
EP22165039.3A 2022-03-29 2022-03-29 Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette Pending EP4254385A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP22165039.3A EP4254385A1 (fr) 2022-03-29 2022-03-29 Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
EP22165039.3A EP4254385A1 (fr) 2022-03-29 2022-03-29 Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette

Publications (1)

Publication Number Publication Date
EP4254385A1 true EP4254385A1 (fr) 2023-10-04

Family

ID=80978871

Family Applications (1)

Application Number Title Priority Date Filing Date
EP22165039.3A Pending EP4254385A1 (fr) 2022-03-29 2022-03-29 Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette

Country Status (1)

Country Link
EP (1) EP4254385A1 (fr)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150228066A1 (en) * 2014-02-10 2015-08-13 Michael Scot Farb Rear Encroaching Vehicle Monitoring And Alerting System
US20190210681A1 (en) * 2016-08-17 2019-07-11 Industry-Academic Cooperation Foundation Chosun University SMART DEVICE-BASED IoT SAFETY SYSTEM FOR BICYCLE RIDING
US20200094821A1 (en) * 2019-10-29 2020-03-26 Lg Electronics Inc. Method and apparatus for controlling vehicle to prevent accident
US20210012663A1 (en) * 2019-07-10 2021-01-14 Peter Cooper System for vehicle monitoring and alerting
US20220073068A1 (en) * 2018-06-13 2022-03-10 Ride Vision Ltd. Rider assistance system and method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150228066A1 (en) * 2014-02-10 2015-08-13 Michael Scot Farb Rear Encroaching Vehicle Monitoring And Alerting System
US20190210681A1 (en) * 2016-08-17 2019-07-11 Industry-Academic Cooperation Foundation Chosun University SMART DEVICE-BASED IoT SAFETY SYSTEM FOR BICYCLE RIDING
US20220073068A1 (en) * 2018-06-13 2022-03-10 Ride Vision Ltd. Rider assistance system and method
US20210012663A1 (en) * 2019-07-10 2021-01-14 Peter Cooper System for vehicle monitoring and alerting
US20200094821A1 (en) * 2019-10-29 2020-03-26 Lg Electronics Inc. Method and apparatus for controlling vehicle to prevent accident

Similar Documents

Publication Publication Date Title
CN110532976B (zh) 基于机器学习和多特征融合的疲劳驾驶检测方法及系统
CN110889351B (zh) 视频检测方法、装置、终端设备及可读存储介质
US9070023B2 (en) System and method of alerting a driver that visual perception of pedestrian may be difficult
US20150116493A1 (en) Method and system for estimating gaze direction of vehicle drivers
CN110619747A (zh) 一种高速公路道路智能监控方法及系统
US20110182473A1 (en) System and method for video signal sensing using traffic enforcement cameras
US8175334B2 (en) Vehicle environment recognition apparatus and preceding-vehicle follow-up control system
CN110866427A (zh) 一种车辆行为检测方法及装置
Battiato et al. On-board monitoring system for road traffic safety analysis
CN102765365A (zh) 基于机器视觉的行人检测方法及行人防撞预警系统
JP6571424B2 (ja) 故障診断装置
EP3847070A1 (fr) Systèmes et procédés de classification de comportement de conducteur
CN110304064B (zh) 一种车辆变道的控制方法及车辆控制系统、车辆
EP2511121B1 (fr) Dispositif et procédé de génération d'un signal d'indication au conducteur d'un véhicule
US20210053572A1 (en) Vehicular driving assist system with traffic jam probability determination
KR102332517B1 (ko) 영상감시 제어장치
CN111046832B (zh) 基于图像识别的逆行判断方法、装置、设备和存储介质
CN110660270A (zh) 车辆碰撞风险评价模型的建立方法和碰撞风险评价方法
CN106183981A (zh) 基于汽车的路障检测方法、装置及汽车
CN110225236B (zh) 为视频监控系统配置参数的方法、装置和视频监控系统
JP2007207274A (ja) 発進報知装置
WO2019021500A1 (fr) Système de détection du nombre d'occupants, procédé de détection du nombre d'occupants et programme
JP6914827B2 (ja) 見落し検知装置、見落し検知方法、およびプログラム
KR20230091400A (ko) 위험도 산출을 통한 지능형 교통 관제시스템
EP4254385A1 (fr) Procédé permettant d'évaluer un risque d'interférence, dispositif de traitement de données, système pour évaluer un risque d'interférence, et ensemble bicyclette

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20221031

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

GRAP Despatch of communication of intention to grant a patent

Free format text: ORIGINAL CODE: EPIDOSNIGR1

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: GRANT OF PATENT IS INTENDED

RIC1 Information provided on ipc code assigned before grant

Ipc: B62J 50/22 20200101ALI20240227BHEP

Ipc: B62J 27/00 20200101ALI20240227BHEP

Ipc: B62J 6/24 20200101ALI20240227BHEP

Ipc: B60Q 9/00 20060101ALI20240227BHEP

Ipc: B60Q 5/00 20060101ALI20240227BHEP

Ipc: B60Q 1/50 20060101ALI20240227BHEP

Ipc: B60W 50/14 20200101ALI20240227BHEP

Ipc: B60W 30/095 20120101ALI20240227BHEP

Ipc: B60W 30/08 20120101ALI20240227BHEP

Ipc: G06V 20/58 20220101ALI20240227BHEP

Ipc: G08G 1/16 20060101AFI20240227BHEP

INTG Intention to grant announced

Effective date: 20240328